Venice AI

Use Venice AI for chat, image generation, embeddings, and more

Actions9

Image → Generate

AI-generated

Overview

The node integrates with Venice AI to generate images from text prompts. It supports advanced image generation features such as specifying negative prompts, image dimensions, inference steps, style presets, and output formats. Users can generate images either with detailed options or via a simpler OpenAI-compatible interface. The node also supports returning images as base64 JSON or binary data.

This node is beneficial for creative workflows where automated image creation is needed based on textual descriptions, such as generating concept art, marketing visuals, or enhancing content with AI-generated imagery.

Practical examples:

  • Creating unique illustrations for blog posts by describing the desired scene.
  • Generating product mockups or design prototypes from textual ideas.
  • Producing stylized avatars or characters using style presets like "Anime" or "3D Model".

Properties

Name Meaning
Model Image generation model to use (e.g., "hidream").
Prompt Text description of the image to generate.
Negative Prompt Elements or concepts that should be excluded from the generated image.
Width Width of the generated image in pixels.
Height Height of the generated image in pixels.
Steps Number of inference steps controlling image generation quality/detail.
CFG Scale Controls how closely the image follows the prompt (higher means stricter adherence).
Seed Random seed for reproducibility of results.
Format Output image format; options are WebP, PNG, JPEG.
Safe Mode Whether to blur adult content in the generated image.
Hide Watermark Option to hide the Venice watermark on the image.
Style Preset Style preset to apply to the image (e.g., "3D Model", "Anime").
Return Binary If true, returns the image as binary data instead of base64 encoded JSON.

Output

  • The node outputs an array of items, each containing a json field.
  • For standard image generation, the json contains the API response with image metadata and base64-encoded image data unless Return Binary is enabled.
  • If Return Binary is enabled, the output item includes a binary property named data containing the raw image file in the specified format (e.g., .webp, .png, .jpeg).
  • This allows downstream nodes to handle the image as a file rather than encoded text.

Dependencies

  • Requires an active Venice AI API key credential configured in n8n.
  • The node makes HTTP POST requests to Venice AI endpoints for image generation.
  • No additional external dependencies beyond the Venice AI service and n8n's built-in HTTP request capabilities.

Troubleshooting

  • Missing binary data error: When using operations like upscale or edit, if the specified binary property does not exist on the input item, the node throws an error indicating the missing binary data property. Ensure the input item contains the correct binary image data under the specified property name.
  • Invalid parameter values: Providing unsupported image dimensions, invalid seeds, or unsupported formats may cause API errors. Validate inputs before execution.
  • API authentication errors: Ensure the Venice AI API key credential is correctly set up and has necessary permissions.
  • Large image sizes or high step counts: May lead to longer processing times or timeouts. Adjust parameters accordingly.
  • Return Binary option: If enabled but downstream nodes do not support binary data, this may cause issues. Use only when binary handling is intended.

Links and References

Discussion